@inproceedings{ghinassi-etal-2024-language,
title = "Language Pivoting from Parallel Corpora for Word Sense Disambiguation of Historical Languages: A Case Study on {L}atin",
author = "Ghinassi, Iacopo and
Tedeschi, Simone and
Marongiu, Paola and
Navigli, Roberto and
McGillivray, Barbara",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.880",
pages = "10073--10084",
abstract = "Word Sense Disambiguation (WSD) is an important task in NLP, which serves the purpose of automatically disambiguating a polysemous word with its most likely sense in context. Recent studies have advanced the state of the art in this task, but most of the work has been carried out on contemporary English or other modern languages, leaving challenges posed by low-resource languages and diachronic change open. Although the problem with low-resource languages has recently been mitigated by using existing multilingual resources to propagate otherwise expensive annotations from English to other languages, such techniques have hitherto not been applied to historical languages such as Latin. In this work, we make the following two major contributions. First, we test such a strategy on a historical language and propose a new approach in this framework which makes use of existing bilingual corpora instead of native English datasets. Second, we fine-tune a Latin WSD model on the data produced and achieve state-of-the-art results on a standard benchmark for the task. Finally, we release the dataset generated with our approach, which is the largest dataset for Latin WSD to date. This work opens the door to further research, as our approach can be used for different historical and, generally, under-resourced languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghinassi-etal-2024-language">
<titleInfo>
<title>Language Pivoting from Parallel Corpora for Word Sense Disambiguation of Historical Languages: A Case Study on Latin</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iacopo</namePart>
<namePart type="family">Ghinassi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Tedeschi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Marongiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">McGillivray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word Sense Disambiguation (WSD) is an important task in NLP, which serves the purpose of automatically disambiguating a polysemous word with its most likely sense in context. Recent studies have advanced the state of the art in this task, but most of the work has been carried out on contemporary English or other modern languages, leaving challenges posed by low-resource languages and diachronic change open. Although the problem with low-resource languages has recently been mitigated by using existing multilingual resources to propagate otherwise expensive annotations from English to other languages, such techniques have hitherto not been applied to historical languages such as Latin. In this work, we make the following two major contributions. First, we test such a strategy on a historical language and propose a new approach in this framework which makes use of existing bilingual corpora instead of native English datasets. Second, we fine-tune a Latin WSD model on the data produced and achieve state-of-the-art results on a standard benchmark for the task. Finally, we release the dataset generated with our approach, which is the largest dataset for Latin WSD to date. This work opens the door to further research, as our approach can be used for different historical and, generally, under-resourced languages.</abstract>
<identifier type="citekey">ghinassi-etal-2024-language</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.880</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10073</start>
<end>10084</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Pivoting from Parallel Corpora for Word Sense Disambiguation of Historical Languages: A Case Study on Latin
%A Ghinassi, Iacopo
%A Tedeschi, Simone
%A Marongiu, Paola
%A Navigli, Roberto
%A McGillivray, Barbara
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ghinassi-etal-2024-language
%X Word Sense Disambiguation (WSD) is an important task in NLP, which serves the purpose of automatically disambiguating a polysemous word with its most likely sense in context. Recent studies have advanced the state of the art in this task, but most of the work has been carried out on contemporary English or other modern languages, leaving challenges posed by low-resource languages and diachronic change open. Although the problem with low-resource languages has recently been mitigated by using existing multilingual resources to propagate otherwise expensive annotations from English to other languages, such techniques have hitherto not been applied to historical languages such as Latin. In this work, we make the following two major contributions. First, we test such a strategy on a historical language and propose a new approach in this framework which makes use of existing bilingual corpora instead of native English datasets. Second, we fine-tune a Latin WSD model on the data produced and achieve state-of-the-art results on a standard benchmark for the task. Finally, we release the dataset generated with our approach, which is the largest dataset for Latin WSD to date. This work opens the door to further research, as our approach can be used for different historical and, generally, under-resourced languages.
%U https://aclanthology.org/2024.lrec-main.880
%P 10073-10084
Markdown (Informal)
[Language Pivoting from Parallel Corpora for Word Sense Disambiguation of Historical Languages: A Case Study on Latin](https://aclanthology.org/2024.lrec-main.880) (Ghinassi et al., LREC-COLING 2024)
ACL